timm/models/ghostnet.py [232:271]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            kernel_conv += _kernel
            bias_conv += _bias

        kernel_final = kernel_conv + kernel_scale + kernel_identity
        bias_final = bias_conv + bias_scale + bias_identity
        return kernel_final, bias_final

    def _fuse_bn_tensor(self, branch):
        if isinstance(branch, ConvBnAct):
            kernel = branch.conv.weight
            running_mean = branch.bn1.running_mean
            running_var = branch.bn1.running_var
            gamma = branch.bn1.weight
            beta = branch.bn1.bias
            eps = branch.bn1.eps
        else:
            assert isinstance(branch, nn.BatchNorm2d)
            if not hasattr(self, 'id_tensor'):
                input_dim = self.in_channels // self.groups
                kernel_value = torch.zeros(
                    (self.in_channels, input_dim, self.kernel_size, self.kernel_size),
                    dtype=branch.weight.dtype,
                    device=branch.weight.device
                )
                for i in range(self.in_channels):
                    kernel_value[i, i % input_dim,
                                 self.kernel_size // 2,
                                 self.kernel_size // 2] = 1
                self.id_tensor = kernel_value
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std

    def switch_to_deploy(self):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/models/ghostnet.py [513:552]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            kernel_conv += _kernel
            bias_conv += _bias

        kernel_final = kernel_conv + kernel_scale + kernel_identity
        bias_final = bias_conv + bias_scale + bias_identity
        return kernel_final, bias_final

    def _fuse_bn_tensor(self, branch):
        if isinstance(branch, ConvBnAct):
            kernel = branch.conv.weight
            running_mean = branch.bn1.running_mean
            running_var = branch.bn1.running_var
            gamma = branch.bn1.weight
            beta = branch.bn1.bias
            eps = branch.bn1.eps
        else:
            assert isinstance(branch, nn.BatchNorm2d)
            if not hasattr(self, 'id_tensor'):
                input_dim = self.in_channels // self.groups
                kernel_value = torch.zeros(
                    (self.in_channels, input_dim, self.kernel_size, self.kernel_size),
                    dtype=branch.weight.dtype,
                    device=branch.weight.device
                )
                for i in range(self.in_channels):
                    kernel_value[i, i % input_dim,
                                 self.kernel_size // 2,
                                 self.kernel_size // 2] = 1
                self.id_tensor = kernel_value
            kernel = self.id_tensor
            running_mean = branch.running_mean
            running_var = branch.running_var
            gamma = branch.weight
            beta = branch.bias
            eps = branch.eps
        std = (running_var + eps).sqrt()
        t = (gamma / std).reshape(-1, 1, 1, 1)
        return kernel * t, beta - running_mean * gamma / std

    def switch_to_deploy(self):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -